Training in progress, step 686663
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +33 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Jun10_17-24-57_2db923e410a0/events.out.tfevents.1686417954.2db923e410a0.29875.0 +2 -2
- runs/Jun10_18-27-22_2db923e410a0/1686421718.1706398/events.out.tfevents.1686421718.2db923e410a0.45518.1 +3 -0
- runs/Jun10_18-27-22_2db923e410a0/events.out.tfevents.1686421718.2db923e410a0.45518.0 +3 -0
- training_args.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3871544599
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3d505118400b8cc65706219c91d9a0c9e09d95df989221176ade7baf15c1bf7
|
3 |
size 3871544599
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b28648855c1812b7c942932e21b3ab1aa9e737a8856b0498e44d5ff6bedae3d3
|
3 |
size 1944201353
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98df663c0d2c6f550aa483476e744f6f0c8c0b14d26daa27cccf7752a403e539
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fb55d22d3c41a6606c4cb3a01f7dfc8dfeeba6f924d365fc5dc46ec19e16d88
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38b62db0464eeffe852cfb7f98cb9fdcf103e71f400d5cd41784ebdf1f318be2
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 17.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -8214,11 +8214,41 @@
|
|
8214 |
"learning_rate": 1.318388022380601e-07,
|
8215 |
"loss": 1.0081,
|
8216 |
"step": 684000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8217 |
}
|
8218 |
],
|
8219 |
"max_steps": 686664,
|
8220 |
"num_train_epochs": 18,
|
8221 |
-
"total_flos": 8.
|
8222 |
"trial_name": null,
|
8223 |
"trial_params": null
|
8224 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 17.999963301213157,
|
5 |
+
"global_step": 686663,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
8214 |
"learning_rate": 1.318388022380601e-07,
|
8215 |
"loss": 1.0081,
|
8216 |
"step": 684000
|
8217 |
+
},
|
8218 |
+
{
|
8219 |
+
"epoch": 17.94,
|
8220 |
+
"learning_rate": 1.541190384118929e-10,
|
8221 |
+
"loss": 1.0351,
|
8222 |
+
"step": 684500
|
8223 |
+
},
|
8224 |
+
{
|
8225 |
+
"epoch": 17.96,
|
8226 |
+
"learning_rate": 9.715872713339514e-11,
|
8227 |
+
"loss": 1.0036,
|
8228 |
+
"step": 685000
|
8229 |
+
},
|
8230 |
+
{
|
8231 |
+
"epoch": 17.97,
|
8232 |
+
"learning_rate": 5.3280415610590384e-11,
|
8233 |
+
"loss": 1.0051,
|
8234 |
+
"step": 685500
|
8235 |
+
},
|
8236 |
+
{
|
8237 |
+
"epoch": 17.98,
|
8238 |
+
"learning_rate": 2.2484333458694384e-11,
|
8239 |
+
"loss": 1.0189,
|
8240 |
+
"step": 686000
|
8241 |
+
},
|
8242 |
+
{
|
8243 |
+
"epoch": 18.0,
|
8244 |
+
"learning_rate": 4.770641833795608e-12,
|
8245 |
+
"loss": 1.0073,
|
8246 |
+
"step": 686500
|
8247 |
}
|
8248 |
],
|
8249 |
"max_steps": 686664,
|
8250 |
"num_train_epochs": 18,
|
8251 |
+
"total_flos": 8.123676033495859e+17,
|
8252 |
"trial_name": null,
|
8253 |
"trial_params": null
|
8254 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c66b8511c8447bf8cefed77f43d3065fb3525af0ff6bef8474faced4e32deedc
|
3 |
size 3771
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b28648855c1812b7c942932e21b3ab1aa9e737a8856b0498e44d5ff6bedae3d3
|
3 |
size 1944201353
|
runs/Jun10_17-24-57_2db923e410a0/events.out.tfevents.1686417954.2db923e410a0.29875.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4508ffec9e376014d67c3740755527327048d0bb90016e1e9197b96c17f37733
|
3 |
+
size 5263
|
runs/Jun10_18-27-22_2db923e410a0/1686421718.1706398/events.out.tfevents.1686421718.2db923e410a0.45518.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6bbe3f8b84ebead3e3f4dd39ba3f4482fb6c0a4080888145ed00463168b58dc
|
3 |
+
size 6187
|
runs/Jun10_18-27-22_2db923e410a0/events.out.tfevents.1686421718.2db923e410a0.45518.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6916063a7da02480eb2f0910d4a0ea9d71383a9733b4ba6ca49ca83f2b415759
|
3 |
+
size 5265
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c66b8511c8447bf8cefed77f43d3065fb3525af0ff6bef8474faced4e32deedc
|
3 |
size 3771
|